analyzing-office365-audit-logs-for-compromise
analyzing-office365-audit-logs-for-compromise is a Blue team & detection skill for AI agents, published by mukul975 in the Anthropic-Cybersecurity-Skills repository on GitHub. Skillspace rates analyzing-office365-audit-logs-for-compromise C (77/100) and it passed the safety scan; a judge model has also reviewed it.
Parse Office 365 Unified Audit Logs via Microsoft Graph API to detect
- Grade
- C
- Quality
- 77 / 100
- Safety
- Passed
- GitHub stars
- 32,716
Placed #4 of 6 in the judged category final for Blue team & detection.
This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.
Our review
- Architecture
- 94 / 100
- Maturity
- Packaged: licensed, with a version or references
- Security scan
- No issues found
- License
- Not declared. Check the repository before reusing it.
Judge review
Placed #4 of 6 in the judged category final for Blue team & detection.
- Trigger
55 55 - Instructions
66 66 - Specificity
70 70 - Safety
88 88 - Disclosure
55 55 - Maintenance
42 42
Correctly scoped Graph permissions (AuditLog.Read.All, MailboxSettings.Read) and accurate BEC indicators (New-InboxRule, Add-MailboxPermission) show real domain knowledge, but the description is cut off mid-sentence and the seven steps are described, never demonstrated with a query or code.
Not checked yet
- Category is a classifier prediction; no model has read this skill yet
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.